agentleFS
Sign inStart free
tomy0000000tomy0000000/skills/alt-text-generator/SKILL.md

alt-text-generator

Skill0 starsChanged 9 months agoMITView on GitHub

Generates accessible alt text descriptions for images for use in web/HTML development. Use this skill whenever a user uploads an image and wants alt text, aria-label copy, or accessibility descriptions. Trigger when the user says anything like "write alt text", "describe this image for accessibility", "what should the alt attribute be", "generate image description for screen readers", or uploads an image in a web dev context. Also trigger when the user is building HTML/components and needs image accessibility attributes filled in.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. casoon/ai-agent-config★ 1same name
    2. eunu-hyudev/threads-writing-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always output the final alt text inside a code block like:

    line 16
  2. Distinctive:

    If there are multiple reasonable interpretations, briefly explain your reasoning before the code block.

    line 22
  3. Distinctive:

    Before writing alt text, identify which image type applies:

    line 28
  4. Distinctive:

    Do not mention visual style ("beautiful", "stunning") — stick to facts

    line 34
  5. Distinctive:

    Ask yourself before writing:

    line 67
  6. Distinctive:

    Never start with "Image of", "Photo of", "Picture of"

    line 78
  7. Distinctive:

    Keep under ~150 characters when possible.

    line 79
  8. Distinctive:

    Don't repeat info already in the surrounding caption or page text (if user shares context)

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Alt Text Generator

Generate accurate, accessible alt attribute text for web images following WCAG 2.1 best practices.

Output Format

  • Length: 2–3 sentences (moderate detail)
  • Tone: Neutral, descriptive, objective — no "image of" or "picture of" prefix
  • Use case: Web/HTML development — output should be ready to paste into alt="..." directly

Always output the final alt text inside a code block like:

alt="Your alt text here."

If there are multiple reasonable interpretations, briefly explain your reasoning before the code block.

Image Type Detection & Handling

Before writing alt text, identify which image type applies:

1. Standard Images (photos, illustrations, icons)

  • Describe the subject, action, and context in 2–3 sentences
  • Focus on information relevant to the surrounding web page context if provided
  • Do not mention visual style ("beautiful", "stunning") — stick to facts
  • Example: alt="A golden retriever puppy sitting on a green lawn, looking up at the camera with its tongue out. The dog wears a red collar with a small tag."

2. Charts & Graphs

  • Identify the chart type (bar, line, pie, etc.)
  • Describe the key data trend or takeaway — not every data point
  • Mention axis labels, units, and approximate values if visible
  • Example: alt="A line chart showing monthly website traffic from January to December 2023. Traffic peaks in July at approximately 120,000 visits, with a secondary peak in November. Overall trend is upward compared to the prior year."

3. Screenshots (UI / App / Web)

  • Identify the application or interface if recognizable
  • Describe the key UI elements and their state visible on screen
  • Include any important text visible in the screenshot
  • Example: alt="A GitHub pull request page showing a merged PR titled 'Fix login bug'. The PR has 3 commits, 2 reviewers approved, and shows a green 'Merged' badge. The diff view shows changes to auth.js."

4. Decorative Images

Decorative images add no informational value (purely aesthetic backgrounds, dividers, abstract textures).

Output:

alt=""

And briefly explain: "This appears decorative — an empty alt attribute tells screen readers to skip it."

Decision Checklist

Ask yourself before writing:

  1. Is this decorative? → Output alt=""
  2. Is this a chart/graph? → Lead with chart type + key insight
  3. Is this a screenshot? → Identify app + describe key UI elements + any visible text
  4. Otherwise → Describe subject, action, context in 2–3 sentences

WCAG Quick Rules

  • Never start with "Image of", "Photo of", "Picture of"
  • Keep under ~150 characters when possible; longer is OK for complex images
  • Don't repeat info already in the surrounding caption or page text (if user shares context)
  • For linked images, describe the destination or action, not just the image content

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free